Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4300 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7671. Min Range: -0.7671

Max Act: 0.7564. Min Act: -0.0000

Data Index: 862164 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 0.7671. Min Range: -0.7671

Max Act: 0.7671. Min Act: -0.0000

Data Index: 360803 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 0.7671. Min Range: -0.7671

Max Act: 0.6762. Min Act: -0.0000

Data Index: 972848 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 0.7671. Min Range: -0.7671

Max Act: 0.7273. Min Act: -0.0000

Data Index: 308453 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.7671. Min Range: -0.7671

Max Act: 0.6800. Min Act: -0.0000

Data Index: 1098852 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 0.7671. Min Range: -0.7671

Max Act: 0.6778. Min Act: -0.0000

Data Index: 1071788 (C4 (Web Text))

Max Activating Token Index: 830

Text #6

Max Range: 0.7671. Min Range: -0.7671

Max Act: 0.6374. Min Act: -0.0000

Data Index: 795181 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 0.7671. Min Range: -0.7671

Max Act: 0.6455. Min Act: -0.0000

Data Index: 203221 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 0.7671. Min Range: -0.7671

Max Act: 0.6041. Min Act: -0.0000

Data Index: 564577 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.7671. Min Range: -0.7671

Max Act: 0.6192. Min Act: -0.0000

Data Index: 574503 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 0.7671. Min Range: -0.7671

Max Act: 0.6228. Min Act: -0.0000

Data Index: 541790 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 0.7671. Min Range: -0.7671

Max Act: 0.6353. Min Act: -0.0000

Data Index: 639708 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 0.7671. Min Range: -0.7671

Max Act: 0.6085. Min Act: -0.0000

Data Index: 145685 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.7671. Min Range: -0.7671

Max Act: 0.6271. Min Act: -0.0000

Data Index: 1286918 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 0.7671. Min Range: -0.7671

Max Act: 0.6060. Min Act: -0.0000

Data Index: 674271 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.7671. Min Range: -0.7671

Max Act: 0.6233. Min Act: -0.0000

Data Index: 1269377 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 0.7671. Min Range: -0.7671

Max Act: 0.6200. Min Act: -0.0000

Data Index: 499562 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 0.7671. Min Range: -0.7671

Max Act: 0.5723. Min Act: -0.0000

Data Index: 615902 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 0.7671. Min Range: -0.7671

Max Act: 0.6111. Min Act: -0.0000

Data Index: 151791 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 0.7671. Min Range: -0.7671

Max Act: 0.4946. Min Act: -0.0000

Data Index: 247674 (C4 (Web Text))

Max Activating Token Index: 764